Consensus scheduling optimizer and optimization method

Abstract

The invention belongs to the technical field of scheduling algorithms, and particularly relates to a consensus scheduling optimizer and an optimization method, and the optimization method comprises the following steps: preference data collection and preprocessing: collecting preference data through a preference data collection module, and preprocessing the data; preference aggregation and analysis: performing aggregation and sorting on individual preferences by using an algorithm for calculating social selection, calculating a collective preference score of each task according to the weight and consistency requirements of voters, and generating a task priority list; optimizing a task scheduling algorithm; and outputting and displaying the scheduling scheme. According to the method, a mode of combining calculation social selection and a task scheduling algorithm is adopted, and preference information of voters can be more accurately captured and analyzed, so that a scheduling scheme which is more in line with collective interests is generated. According to the intelligent scheduling mode, manual intervention and subjective judgment can be greatly reduced, and the scheduling efficiency and accuracy are improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of scheduling algorithms, and in particular relates to a consensus scheduling optimizer and an optimization method. Background Art

[0002] In the field of scheduling algorithms, with the continuous development and popularization of computer technology, the increase in system scale and complexity has made task scheduling issues more and more important. Traditional scheduling algorithms are often based on a single optimization goal, such as minimizing job completion time or maximizing system throughput. However, in practical applications, it is often necessary to consider multiple optimization goals and constraints at the same time, which makes the scheduling problem more complicated. Therefore, studying scheduling algorithms that can handle multiple goals and multiple constraints has become an important research direction.

[0003] Social choice and preference aggregation are important branches in the field of artificial intelligence and decision support systems. In real life, many decision-making problems involve multiple stakeholders or voters who may have different preferences and opinions on the decision results. How to effectively aggregate these preferences and generate decision results that are in line with the collective interest is a challenging problem. In recent years, with the development of computational social choice theory, researchers have proposed a series of algorithms and models for processing and analyzing preference data to achieve fair and effective decision-making.

[0004] In a distributed system, multiple nodes need to work together to complete complex tasks. Since there may be communication delays and data inconsistencies between nodes, how to achieve efficient task scheduling and resource allocation has become a key issue. The development of cloud computing technology has made large-scale computing and data storage possible, but it has also put forward higher requirements for task scheduling. Summary of the invention

[0005] In response to the above technical problems of communication delay and data inconsistency in distributed systems, the present invention provides a consensus scheduling optimizer and optimization method, which achieves the aggregation of multiple voters' preference information and the optimization of task execution order by combining computational social selection and task scheduling algorithms. Through clear functional modules and logical processes, efficient and fair task scheduling is achieved, improving the overall performance of the system.

[0006] In order to solve the above technical problems, the technical solution adopted by the present invention is:

[0007] A consensus scheduling optimizer includes a preference data collection module, a preference aggregation module, a task scheduling algorithm module and a result output module, wherein the preference data collection module is responsible for collecting preference data from each voter; the preference data collection module is connected to a preference aggregation module, and the preference aggregation module aggregates and analyzes individual preferences based on the collected preference data using algorithms and models of computational social choice; the preference aggregation module is connected to a task scheduling algorithm module, and the task scheduling algorithm module generates an optimized task scheduling plan based on the output of the preference aggregation module and the task scheduling algorithm; the task scheduling algorithm module is connected to a result output module, and the result output module outputs the scheduling plan generated by the task scheduling algorithm module in a visual or textual form.

[0008] An optimization method for a consensus scheduling optimizer comprises the following steps:

[0009] S1, preference data collection and preprocessing, collecting preference data through the preference data collection module and preprocessing the data;

[0010] S2, preference aggregation and analysis, using the algorithm of computational social choice to aggregate and sort individual preferences, calculate the collective preference score of each task according to the voter weight and consistency requirements, and generate a task priority list;

[0011] S3, task scheduling algorithm optimization, based on the task priority list, combined with the task scheduling algorithm, considering the task dependencies, resource limitations and time constraints, and finding the optimal task execution order through the optimization algorithm;

[0012] S4. Output and display of scheduling plan: Output the optimized task scheduling plan in the form of visual charts or text reports, showing the key information of task execution order and estimated completion time. Users can adjust or confirm as needed to execute the scheduling plan.

[0013] The method for collecting preference data in S1 is: collecting voter preference data through a user interface, which may include information on voting options, voting time, and voting results, and obtaining voting data from other data sources through an API or other system interface.

[0014] The method for preprocessing data in S1 is: performing data cleaning, formatting and normalization operations to ensure the accuracy and consistency of the data; data cleaning: checking and deleting duplicate data records to ensure the uniqueness and independence of the data; for missing data, using interpolation, deletion or filling methods to process; correcting outliers according to business logic or data distribution to ensure data accuracy; removing meaningless characters such as stop words, punctuation marks, etc. to improve data quality; data formatting: converting all data into a unified format, including standardized date format and unified units; ensuring that the data type is correct, converting the date field into a date and time type; data normalization: scaling the data to a specified range for easy comparison and analysis, and converting the data into a standard normal distribution with a mean of 0 and a variance of 1.

[0015] The method of preference aggregation and analysis in S2 is:

[0016] S2.1, Preference aggregation: Use the aggregation procedure in social choice theory to process these preference information; Borda rule determines the social preference ranking of each option by calculating the total ranking score of all preferences;

[0017] S2.2. Weight and consistency requirements: In the aggregation process, it is important to consider the weight of voters. The weight reflects the influence or credibility of voters in the group. The consistency requirement ensures that the aggregation results can reasonably reflect the preferences of the group.

[0018] S2.3. Calculate collective preference scores: Calculate the collective preference score of each task based on the aggregated preference information by weighted summing up the preference scores of all voters; introduce dynamic programming methods to optimize the calculation process to avoid the cost of exponential complexity;

[0019] S2.4. Generate a task priority list: Finally, generate a task priority list based on the calculated collective preference score. The priority list can be arranged from high to low according to the score to determine which tasks should be executed first; other factors such as information cost and group wisdom can be combined for adjustment to improve the accuracy and fairness of decision-making.

[0020] The method for optimizing the task scheduling algorithm in S3 is:

[0021] S3.1, Construction of the task priority list: Assign a priority to each task based on factors such as task importance, urgency, and time sensitivity; Use a binary multi-point interpolation method to determine the unique priority of the task, combining the relative deadlines and idle time of the tasks;

[0022] S3.2, Selection and optimization of task scheduling algorithm: Select the list scheduling algorithm List Scheduling, which is implemented by scanning the task list and processing the first executable task; for heterogeneous multi-core processors, adopt an improved priority list task scheduling algorithm, which is based on the performance differences of heterogeneous cores and the weighted priority of dependent task characteristics;

[0023] S3.3, Consider task dependencies: In the process of task scheduling, the priority of tasks is determined by calculating the out-degree, communication cost and average cost of each task; the topological traversal method is used to ensure the timing relationship between tasks, and priority rules such as critical path tasks first, backward impact and minimum idle time are adopted for task scheduling and resource allocation;

[0024] S3.4. Handling of resource constraints: In the case of resource constraints, heuristic methods are used to find schedulable implementations to ensure that the application constraints are guaranteed; the parallel ant colony optimization ACO algorithm is used to sort tasks under resource constraints in the mixed integer programming MIP to efficiently obtain feasible solutions with resources and priorities;

[0025] S3.5. Management of time constraints: In task scheduling, the deadline and expected launch time of the task need to be considered to minimize the deviation rate of task execution time; use belief networks to optimize task scheduling;

[0026] S3.6, Application of optimization algorithm: Use backtracking method combined with pruning strategy to find the optimal scheduling solution, recursively traverse all possible scheduling solutions and use greedy algorithm to get suboptimal solution; introduce heuristic methods, including HEFT algorithm and CPOP algorithm, to optimize processor selection by calculating the average computing cost, communication cost and critical path length of task nodes;

[0027] S3.7 Scheduling of real-time systems: In real-time operating systems, implement automatic task priority scheduling algorithms to ensure priority execution of high-priority tasks; use reinforcement learning methods to improve time utilization and output, and optimize real-time scheduling of parallel tasks through simulation models, Markov decision processes, and policy networks.

[0028] The method for outputting and displaying the scheduling plan in S4 is:

[0029] S4.1 Visual interface design: Use a graphical interface to display the execution order and estimated completion time of tasks. The graphical interface includes Gantt charts, network diagrams, lists or line graphs to intuitively display the start and end dates of tasks, milestones, and dependencies between activities;

[0030] S4.2, Report generation and data analysis: Provides report generation tools, through which users can understand the execution efficiency of tasks and resource utilization in order to optimize and improve them; supports access to multiple data sources and provides data analysis tools to help users deeply understand the effects of scheduling plans.

[0031] Compared with the prior art, the present invention has the following beneficial effects:

[0032] 1. Compared with traditional scheduling methods, this invention adopts a combination of computational social choice and task scheduling algorithm, which can more accurately capture and analyze voters' preference information, thereby generating a scheduling plan that is more in line with collective interests. This intelligent scheduling method can greatly reduce manual intervention and subjective judgment, and improve the efficiency and accuracy of scheduling.

[0033] 2. Through the open and transparent preference aggregation and scheduling calculation process, the consensus scheduling optimizer of the present invention can ensure that the opinions of each voter are fully considered, effectively avoid human intervention and bias, and enhance the fairness and transparency of scheduling. This improvement in fairness and transparency helps to build trust, reduce conflicts, and promote cooperation and consensus.

[0034] 3. The consensus scheduling optimizer of the present invention can generate the optimal task scheduling scheme by comprehensively considering factors such as task priority, dependency, resource limitation, etc. This scheme can optimize resource allocation, reduce resource waste and conflict, and improve the overall performance and stability of the system. At the same time, through reasonable task arrangement, the operating cost and maintenance cost of the system can also be reduced. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the implementation methods of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for the implementation methods or the description of the prior art. Obviously, the drawings in the following description are only exemplary, and for ordinary technicians in this field, other implementation drawings can be derived from the provided drawings without creative work.

[0036] The structures, proportions, sizes, etc. illustrated in this specification are only used to match the contents disclosed in the specification so as to facilitate understanding and reading by persons familiar with the technology. They are not used to limit the conditions under which the present invention can be implemented, and therefore have no substantial technical significance. Any structural modification, change in proportion or adjustment of size shall still fall within the scope of the technical contents disclosed in the present invention without affecting the effects and purposes that can be achieved by the present invention.

[0037] Figure 1 It is a flow chart of the steps of the present invention. DETAILED DESCRIPTION

[0038] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments. These descriptions are only to further illustrate the features and advantages of the present invention, rather than to limit the claims of the present invention. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0039] The specific implementation of the present invention is further described in detail below in conjunction with the accompanying drawings and examples. The following examples are used to illustrate the present invention, but are not intended to limit the scope of the present invention.

[0040] In the description of this application, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0041] This embodiment provides a consensus scheduling optimizer, including a preference data collection module, a preference aggregation module, a task scheduling algorithm module and a result output module. The preference data collection module is responsible for collecting preference data from each voter. The preference data collection module is connected to the preference aggregation module. The preference aggregation module aggregates and analyzes individual preferences based on the collected preference data and uses the algorithm and model of computational social choice. The preference aggregation module is connected to the task scheduling algorithm module. The task scheduling algorithm module generates an optimized task scheduling plan based on the output of the preference aggregation module and the task scheduling algorithm. The task scheduling algorithm module is connected to the result output module. The result output module outputs the scheduling plan generated by the task scheduling algorithm module in a visual or textual form.

[0042] An optimization method for a consensus scheduling optimizer, such as Figure 1 As shown, the following steps are included:

[0043] Step 1: Collect preference data through the preference data collection module and pre-process the data. Collect voter preference data through the user interface. The data may include information about voting options, voting time, and voting results. Obtain voting data from other data sources through APIs or other system interfaces.

[0044] Perform data cleaning, formatting, and normalization operations to ensure data accuracy and consistency. Data cleaning: Check and delete duplicate data records to ensure data uniqueness and independence. For missing data, use interpolation, deletion, or filling methods to handle it. Correct outliers based on business logic or data distribution to ensure data accuracy. Remove meaningless characters such as stop words, punctuation, etc. to improve data quality. Data formatting: Convert all data to a unified format, including standardized date format and unified units. Ensure that the data type is correct and convert date fields to date and time types. Data normalization: Scale the data to a specified range for easy comparison and analysis, and convert the data to a standard normal distribution with a mean of 0 and a variance of 1.

[0045] Step 2: Preference aggregation and analysis: Use the algorithm of computational social choice to aggregate and sort individual preferences, calculate the collective preference score of each task based on the voter weights and consistency requirements, and generate a task priority list.

[0046] Step 2.1, preference aggregation: Use the aggregation procedure in social choice theory to process these preference information. Borda rule determines the social preference ranking of each option by calculating the total ranking score of all preferences.

[0047] Step 2.2, weight and consistency requirements: In the aggregation process, it is important to consider the weight of the voter. The weight reflects the influence or credibility of the voter in the group. The consistency requirement ensures that the aggregation result can reasonably reflect the preferences of the group.

[0048] Step 2.3, Calculate collective preference score: Based on the aggregated preference information, calculate the collective preference score of each task by weighted summing the preference scores of all voters. Dynamic programming method is introduced to optimize the calculation process to avoid the cost of exponential complexity.

[0049] Step 2.4, generate a task priority list: Finally, based on the calculated collective preference score, generate a task priority list, which can be arranged from high to low according to the score to determine which tasks should be executed first. Other factors such as information cost and group wisdom can be combined to improve the accuracy and fairness of decision-making.

[0050] Step 3: Optimize the task scheduling algorithm. Based on the task priority list and combined with the task scheduling algorithm, consider the task dependencies, resource limitations, and time constraints, and find the optimal task execution order through the optimization algorithm.

[0051] Step 3.1, Construction of Task Priority List: Assign a priority to each task based on its importance, urgency, and time sensitivity. Use a binary multi-point interpolation method to determine the unique priority of the task, combined with the relative deadline and idle time of the task.

[0052] Step 3.2, selection and optimization of task scheduling algorithm: Select the list scheduling algorithm List Scheduling, which is implemented by scanning the task list and processing the first executable task. For heterogeneous multi-core processors, an improved priority list task scheduling algorithm is used, which is based on the performance differences of heterogeneous cores and the weighted priority of dependent task characteristics.

[0053] Step 3.3, consider task dependencies: In the task scheduling process, the priority of tasks is determined by calculating the out-degree, communication cost and average cost of each task. The topological traversal method is used to ensure the timing relationship between tasks, and priority rules such as critical path tasks first, backward impact and minimum idle time are used for task scheduling and resource allocation.

[0054] Step 3.4, handling resource constraints: In the case of resource constraints, heuristic methods are used to find schedulable implementations to ensure that the application constraints are guaranteed. The parallel ant colony optimization ACO algorithm is used to sort tasks under resource constraints in the mixed integer programming MIP to efficiently obtain feasible solutions with resources and priorities.

[0055] Step 3.5, Time Constraint Management: In task scheduling, the deadline and expected launch time of the task need to be considered to minimize the deviation rate of task execution time. Use Belief Networks to optimize task scheduling.

[0056] Step 3.6, Application of optimization algorithm: Use backtracking method combined with pruning strategy to find the optimal scheduling solution, recursively traverse all possible scheduling solutions and use greedy algorithm to get the suboptimal solution. Introduce heuristic methods, including HEFT algorithm and CPOP algorithm, to optimize processor selection by calculating the average computing cost, communication cost and critical path length of task nodes.

[0057] Step 3.7, real-time system scheduling: In the real-time operating system, implement the automatic scheduling algorithm of task priority to ensure the priority execution of high-priority tasks. Use reinforcement learning methods to improve time utilization and output, and optimize the real-time scheduling of parallel tasks through simulation models, Markov decision processes and policy networks.

[0058] Step 4: Output and display the scheduling plan. Output the optimized task scheduling plan in the form of a visual chart or text report, showing the key information of the task execution order and estimated completion time. Users can adjust or confirm as needed to execute the scheduling plan.

[0059] Step 4.1, visual interface design: Use a graphical interface to display the execution order and estimated completion time of tasks. The graphical interface includes Gantt charts, network diagrams, lists or line graphs to intuitively display the start and end dates of tasks, milestones, and dependencies between activities.

[0060] Step 4.2, Report generation and data analysis: Provide report generation tools, users can understand the execution efficiency of tasks and resource utilization through reports, so as to optimize and improve. Support multiple data source access, provide data analysis tools, help users deeply understand the effect of scheduling solutions.

[0061] Embodiment 1

[0062] In a large enterprise, multiple departments need to share conference rooms for meetings and training activities. Since the number of conference rooms is limited and the time and scale of conference room requirements vary from department to department, an intelligent conference room scheduling system is needed to ensure the rational allocation and use of resources.

[0063] By implementing a consensus scheduling optimizer, the intelligent conference room scheduling system can collect conference room usage needs of various departments, including preference information such as meeting time, number of people, and required facilities. Based on this information, the system combines the computational social choice algorithm to generate a conference room usage plan that meets collective preferences. For example, a department may have a special preference for a specific conference room, while other departments may pay more attention to the availability and size of the conference room. By comprehensively considering these factors, the system is able to generate a scheduling plan that meets the needs of each department and maximizes the efficiency of conference room use.

[0064] In actual applications, the intelligent conference room scheduling system can update the reservation status and usage of the conference room in real time, and provide an intuitive reservation interface and notification mechanism for each department. At the same time, the system can also dynamically adjust and optimize according to the real-time occupancy of the conference room and the changes in the needs of each department to ensure the effective use of resources.

[0065] Embodiment 2

[0066] In a cloud computing environment, multiple users and applications need to share and compete for computing resources, such as CPU, memory, and storage. In order to achieve fair and efficient allocation of resources, the cloud computing resource allocation platform introduces a consensus scheduling optimizer.

[0067] The platform collects information such as user resource requirements and application workload characteristics, and uses the computational social selection algorithm to aggregate preferences and generate a resource allocation priority list that reflects collective preferences. At the same time, combined with the task scheduling algorithm, the platform can comprehensively consider task dependencies, resource constraints, and performance requirements to generate the optimal resource allocation plan.

[0068] In actual applications, cloud computing resource allocation platforms can perform real-time resource scheduling and allocation based on users' real-time needs and dynamic changes in resources. By dynamically adjusting the number, configuration, and location of virtual machines, the platform can ensure that users' computing tasks are executed in a timely and efficient manner while avoiding resource waste and conflicts.

[0069] Only the preferred embodiments of the present invention are described in detail above, but the present invention is not limited to the above embodiments. Various changes can be made within the knowledge scope of ordinary technicians in this field without departing from the purpose of the present invention, and various changes should be included in the protection scope of the present invention.

Claims

1. A consensus scheduling optimizer, characterized by: It includes a preference data collection module, a preference aggregation module, a task scheduling algorithm module and a result output module. The preference data collection module is responsible for collecting preference data from each voter; The preference data collection module is connected to the preference aggregation module, and the preference aggregation module aggregates and analyzes individual preferences based on the collected preference data and uses the algorithms and models of computational social choice; the preference aggregation module is connected to the task scheduling algorithm module, and the task scheduling algorithm module generates an optimized task scheduling plan based on the output of the preference aggregation module and the task scheduling algorithm; the task scheduling algorithm module is connected to the result output module, and the result output module outputs the scheduling plan generated by the task scheduling algorithm module in a visual or textual form.

2. The optimization method of a consensus scheduling optimizer according to claim 1, characterized in that: The following steps are involved: S1, preference data collection and preprocessing, collecting preference data through the preference data collection module and preprocessing the data; S2, preference aggregation and analysis, using the algorithm of computational social choice to aggregate and sort individual preferences, calculate the collective preference score of each task according to the voter weight and consistency requirements, and generate a task priority list; S3, task scheduling algorithm optimization, based on the task priority list, combined with the task scheduling algorithm, considering the task dependencies, resource limitations and time constraints, and finding the optimal task execution order through the optimization algorithm; S4. Output and display of scheduling plan: Output the optimized task scheduling plan in the form of visual charts or text reports, showing the key information of task execution order and estimated completion time. Users can adjust or confirm as needed to execute the scheduling plan.

3. The optimization method of a consensus scheduling optimizer according to claim 2, characterized in that: The method for collecting preference data in S1 is: collecting voter preference data through a user interface, which may include information on voting options, voting time, and voting results, and obtaining voting data from other data sources through an API or other system interface.

4. The optimization method of a consensus scheduling optimizer according to claim 2, characterized in that: The method of preprocessing the data in S1 is: performing data cleaning, formatting and normalization operations to ensure the accuracy and consistency of the data; data cleaning: checking and deleting duplicate data records to ensure the uniqueness and independence of the data; for missing data, using interpolation, deletion or filling methods to process; correcting outliers according to business logic or data distribution to ensure data accuracy; removing meaningless characters such as stop words, punctuation marks, etc. to improve data quality; data Formatting: Convert all data into a unified format, including standardized date format and unified units; ensure that the data type is correct and convert date fields into date and time types; Data normalization: Scale the data to a specified range for easier comparison and analysis, and convert the data to a standard normal distribution with a mean of 0 and a variance of 1.

5. The optimization method of a consensus scheduling optimizer according to claim 2, characterized in that: The method of preference aggregation and analysis in S2 is: S2.1, Preference aggregation: Use the aggregation procedure in social choice theory to process these preference information; Borda rule determines the social preference ranking of each option by calculating the total ranking score of all preferences; S2.

2. Weight and consistency requirements: In the aggregation process, it is important to consider the weight of voters. The weight reflects the influence or credibility of voters in the group. The consistency requirement ensures that the aggregation results can reasonably reflect the preferences of the group. S2.

3. Calculate collective preference scores: Calculate the collective preference score of each task based on the aggregated preference information by weighted summing up the preference scores of all voters; introduce dynamic programming methods to optimize the calculation process to avoid the cost of exponential complexity; S2.4, Generate task priority list: Finally, based on the calculated collective preference scores, generate a task priority list. The priority list can be arranged from high to low according to the scores, so as to determine which tasks should be executed first; Other factors such as information cost and group wisdom are combined to make adjustments to improve the accuracy and fairness of decision-making.

6. The optimization method of a consensus scheduling optimizer according to claim 2, characterized in that: The method for optimizing the task scheduling algorithm in S3 is: S3.1, Construction of the task priority list: Assign a priority to each task based on factors such as task importance, urgency, and time sensitivity; Use a binary multi-point interpolation method to determine the unique priority of the task, combining the relative deadlines and idle time of the tasks; S3.2, Selection and optimization of task scheduling algorithm: Select the list scheduling algorithm List Scheduling, which is implemented by scanning the task list and processing the first executable task; for heterogeneous multi-core processors, adopt an improved priority list task scheduling algorithm, which is based on the performance differences of heterogeneous cores and the weighted priority of dependent task characteristics; S3.3, Consider task dependencies: In the process of task scheduling, the priority of tasks is determined by calculating the out-degree, communication cost and average cost of each task; the topological traversal method is used to ensure the timing relationship between tasks, and priority rules such as critical path tasks first, backward impact and minimum idle time are adopted for task scheduling and resource allocation; S3.4, Handling resource constraints: In the case of resource constraints, heuristic methods are used to find schedulable implementations to ensure that the application constraints are guaranteed; The parallel ant colony optimization (ACO) algorithm is used to sort tasks under resource constraints in mixed integer programming (MIP) to efficiently obtain feasible solutions with resources and priorities. S3.

5. Management of time constraints: In task scheduling, the deadline and expected launch time of the task need to be considered to minimize the deviation rate of task execution time; use belief networks to optimize task scheduling; S3.6, Application of optimization algorithm: Use backtracking method combined with pruning strategy to find the optimal scheduling solution, recursively traverse all possible scheduling solutions and use greedy algorithm to get suboptimal solution; introduce heuristic methods, including HEFT algorithm and CPOP algorithm, to optimize processor selection by calculating the average computing cost, communication cost and critical path length of task nodes; S3.7 Scheduling of real-time systems: In real-time operating systems, implement automatic task priority scheduling algorithms to ensure priority execution of high-priority tasks; use reinforcement learning methods to improve time utilization and output, and optimize real-time scheduling of parallel tasks through simulation models, Markov decision processes, and policy networks.

7. The optimization method of a consensus scheduling optimizer according to claim 2, characterized in that: The method for outputting and displaying the scheduling plan in S4 is: S4.1 Visual interface design: Use a graphical interface to display the execution order and estimated completion time of tasks. The graphical interface includes Gantt charts, network diagrams, lists or line graphs to intuitively display the start and end dates of tasks, milestones, and dependencies between activities; S4.2, Report generation and data analysis: Provides report generation tools, through which users can understand the execution efficiency of tasks and resource utilization in order to optimize and improve them; supports access to multiple data sources and provides data analysis tools to help users deeply understand the effects of scheduling plans.

Images